ScaleDown: Summarize vs Thinking Machines: Inkling
On input price, ScaleDown: Summarize is ~25.0× cheaper. Verified 2026-10-21.
ScaleDown: Summarize $0.040/FreevsThinking Machines: Inkling $1.00/$4.05
Verdict
On blended price (3:1 input:output), ScaleDown: Summarize is ~58.8× cheaper ($0.040/Free vs $1.00/$4.05 per 1M tokens).
Pricing
Per-million-token list prices, verified 2026-10-21. Green marks the better value.
| Metric | ScaleDown: Summarize | Thinking Machines: Inkling |
|---|---|---|
| Input / 1M | $0.040 | $1.00 |
| Output / 1M | Free | $4.05 |
| Cache read / 1M | — | $0.170 |
| Blended (3:1) | $0.030/1M | $1.76/1M |
| Estimated monthly cost | ScaleDown: Summarize | Thinking Machines: Inkling |
|---|---|---|
| Chatbot10,000 reqs · 800/400 tok | $0.32 | $24.20 |
| Coding agent5,000 reqs · 8000/2000 tok | $1.60 | $80.50 |
| RAG pipeline30,000 reqs · 4000/500 tok | $4.80 | $180.75 |
Plug in your own numbers in the calculator, or paste a real bill into the Bill Shredder.
Specifications & capabilities
| Metric | ScaleDown: Summarize | Thinking Machines: Inkling |
|---|---|---|
| Context window | 1M | 524K |
| Max output | 4K | 472K |
| Vision input | ✓ | ✓ |
| Tool calling | – | ✓ |
| Reasoning | – | ✓ |
Provider
Infrastructure metrics for the organizations behind these models.
| Metric | scaledown | Thinking Machines Lab |
|---|---|---|
| Listed endpoints | — | 3 |
| Reliability | — | 99.3% |
| Avg latency | — | 480 ms |
| Pricing tiers | — | standard, free, batch |
Full details: ScaleDown: Summarize pricing · Thinking Machines: Inkling pricing